ai-forever/pollux-judge-7b
Full fine-tune vs t-tech/T-lite-it-1.0. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 56/57, MLP 84/84, Attention 196/196, lm_head 1/1
Full fine-tune vs t-tech/T-lite-it-1.0. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 56/57, MLP 84/84, Attention 196/196, lm_head 1/1